Objective To assess the dignosis value of CT three-dimensional reconstruction with Fisher discriminant model in small solitary pulmonary nodules before operation.Methods CT data of 40 cases with SPN were retrospectively analyzed and divided into into malignant pulmonary nodules (25 cases),squamous cell carcinoma (4 cases),adenocarcinoma (13 cases),lung cancer (4 ca-ses),small cell lung cancer (2 cases),large cell carcinoma (1 case),metastases tumor (1 case),benign nodules (1 5 cases,6 cases of tuberculosis,2 cases of hamartoma,and 7 cases of non-specific inflammatory nodules)by pathology and follow-up results.The CT features of pulmonary nodules were evaluated through multi-planar reformation (MPR),curved-planar reformation (CPR),volume rendering (VR),maximum intensity proj ection (MIP)and other three-dimensional reconstruction.The three-dimensional data were divided into benign and malignant groups.In each of the two groups,the significant signs of morphological signs of discrimination indicators were adminstrated Fisher discriminant,and the probalitiy of false positives were estimated using cross-validation method. Results The positive features of pulmonary nodules in there-dismensional images were much more than in two-dimensional images. Fisher discriminant formula of solitary pulmonary nodules in three-dimensional images was Z=1.143X1 + 0.454X2+1.606X3-0.262X4+0.04X5+0.483X6+1.611X7-2.164.Discriminant boundary value Zc was-0.516.When Zcgreater than -0.516,nodules were proneed to considere as malignant nodules.In 25 cases of malignant nodules,4 cases mistook for benign.When Zc less than -0.516,nodules were proneed to considere as benign nod-ules.In 1 5 benign nodules,2 cases mistook for malignant.The total misdiagnosis and accuracy rate were 15 % and 85% respec-tively.Conclusion CT three-dimensional reconstruction combined with Fisher discriminant model have a high clinical value in dif-fereiating diagonsis of pulmonary nodules were proneed to considere as malignant nodules.In 25 cases of malignant nodules,4 cases mistook for benign.When Zc less than -0.516,nodules were proneed to considere as benign nodules. In 15 benign nodules,2 cases mistook for malignant.The total misdiagnosis and accuracy rate were 15 % and 85% respec-tively.Conclusion CT three-dimensional reconstruction combined with Fisher discriminant model have a high clinical value in differeiating diagonsis of pulmonary nodules.

Objective:To construct a risk prediction model for the inter-hospital transfer of critically ill children using machine learning methods, identify key medical features affecting transfer outcomes, and improve the success rate of transfers.Methods:A prospective study was conducted on critically ill children admitted to the pediatric transfer center of Hunan Children's Hospital from January 2020 to January 2021. Medical data on critical care features and relevant data from the Pediatric Risk of Mortality (PRISMⅢ) scoring system were collected and processed. Three machine learning models, including logistic regression, decision tree, and Relief algorithm, were used to construct the risk prediction model. A back propagation neural network was employed to build a referral outcome prediction model to verify and analyze the selected medical features from the risk prediction model, exploring the key medical features influencing inter-hospital transfer risk.Results:Among the 549 transferred children included in the study, 222 were neonates (40.44%) and 327 were non-neonates (59.56%). There were 50 children in-hospital deaths, resulting in a mortality rate of 9.11%. After processing 151 critical care medical feature data points, each model selected the top 15 important features influencing transfer outcomes, with a total of 34 selected features. The decision tree model had an overlap of 72.7% with PRISMⅢ indicators, higher than logistic regression (36.4%) and Relief algorithm (27.3%). The training prediction accuracy of the decision tree model was 0.94, higher than the accuracy of 0.90 when including all features, indicating its clinical utility. Among the top 15 important features selected by the decision tree model, the impact on transfer outcomes was ranked as follows based on quantitative feature violin plots: base excess, total bilirubin, ionized calcium, total time, arterial oxygen pressure, blood parameters (including white blood cells, platelets, prothrombin time/activated partial thromboplastin time), carbon dioxide pressure, blood glucose, systolic blood pressure, heart rate, organ failure, lactate, capillary refill time, temperature, and cyanosis. Eight of these important features overlapped with PRISMⅢ indicators, including systolic blood pressure, heart rate, temperature, pupillary reflex, consciousness, acidosis, arterial oxygen pressure, carbon dioxide pressure, blood parameters, and blood glucose. The decision tree was used to select the top 15 medical features with high impact on the neonatal and non-neonatal datasets, respectively. A total of 19 features were selected, among which there were 8 differences and 11 overlap terms between the important features of the neonatal and non-neonatal.Conclusions:Machine learning models could serve as reliable tools for predicting the risk of inter-hospital transfer of critically ill children. The decision tree model exhibits superior performance and helps identify key medical features affecting inter-hospital transfer risk, thereby improving the success rate of inter-hospital transfers for critically ill children.

Objective To explore the value of non-contrast CT findings of acute ischemic stroke(AIS)for predicting early prognosis after mechanical thrombectomy.Methods Data of 161 AIS patients from clinical center 1 who underwent mechanical thrombectomy were retrospectively analyzed.The patients were divided into training set(n=113)and internal test set(n=48)at the ratio of 7∶3,while 79 AIS patients who underwent mechanical thrombectomy from clinical center 2 were retrospectively enrolled as external test set.According to the National Institutes of Health stroke scale(NIHSS)scores 7 days after thrombectomy,patients'prognosis were classified as good(＜15 points)or poor(≥15 points).Pre-treatment non-contrast CT images of patients were reviewed,and CT findings were comparatively analyzed.Independent predictors of patients'early prognosis after mechanical thrombectomy were obtained with sequential univariate and multivariate logistic regressions,and a predicting model was established and visualized as a nomogram.The receiver operating characteristic curve was drawn,and the distinction was assessed with the area under the curve(AUC),then calibration was assessed with Hosmer-Lemeshow goodness of fit test,and the net benefit was evaluated with decision curve analysis(DCA).Results Alberta stroke program early CT score(ASPECTS),hyperdense middle cerebral artery sign(HMCAS)and basal ganglia calcification were all independent predictors of early prognosis of AIS after mechanical thrombectomy(all P＜0.05).The predictive model was established combining the above 3 variables and then visualized as a nomogram to predict prognosis of AIS after mechanical thrombectomy,with AUC of 0.776 in internal test set(χ2=6.052,P=0.417)and 0.800 in external test set(χ2=2.269,P=0.811).DCA showed that the nomogram might provide clinical net benefit within certain threshold probability ranges.Conclusion ASPECTS,HMCAS and basal ganglia calcification were all independent predictors of early prognosis of AIS after mechanical thrombectomy.The nomogram originated from predicting model combining the three could be used to somewhat accurately predict poor early prognosis after mechanical thrombectomy.